INDEX

Explanations

discussions of scientific hypotheses and classifications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soever

-0.55

UnknownFieldSet

-0.55

⋙

-0.54

figsize

-0.54

AddTagHelper

-0.54

rxjs

-0.53

hyrchwyd

-0.51

tagHelperRunner

-0.51

ⓧ

-0.48

AnchorStyles

-0.48

POSITIVE LOGITS

 morire

0.63

 newBuilder

0.62

djangoproject

0.60

 plais

0.58

 juridiques

0.57

 esquerdo

0.57

 dianteiro

0.56

 OFDb

0.56

 anteriore

0.56

 esquerda

0.55

Activations Density 0.666%

discussions of scientific hypotheses and classifications

No Comments

No Known Activations